© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 88532
    Prev
    Next
    INDEX
    Explanations

    right or east orientation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tres
    -0.12
     forth
    -0.11
    /Object
    -0.11
    onis
    -0.11
     Rounds
    -0.11
     Sac
    -0.11
     trump
    -0.11
    ANY
    -0.11
    /he
    -0.11
    pled
    -0.11
    POSITIVE LOGITS
     alternating
    0.09
     trying
    0.09
     rapidly
    0.09
     altern
    0.08
     sock
    0.08
     Jenner
    0.07
    alsa
    0.07
     Trying
    0.07
    between
    0.07
     between
    0.07
    Activations Density 0.009%

    No Known Activations